Fig 1.
Illustrative block diagram of the proposed COVID-19 detection system.
Fig 2.
PCA steps.
Fig 3.
Feature extraction steps.
Table 1.
Parameters of the ELM and OGA [28].
Fig 4.
Diagram of the arithmetic crossover and uniform mutation operations example.
Fig 5.
Pseudocode of the OGA-ELM [28].
Fig 6.
OGA-ELM’s flowchart [28].
Fig 7.
Description of the dataset.
Table 2.
Feature extraction step dimensionality for single image and entire dataset images.
Fig 8.
Accuracy results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 9.
Precision results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 10.
Recall results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 11.
F-measure results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 12.
G-mean results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 13.
True positive results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 14.
True negative results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 15.
False positive results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 16.
False negative results of the OGA–ELM model using random, K-tournament, and roulette wheel.
Fig 17.
ROC of the OGA–ELM for the highest result.
Table 3.
Evaluation results based on OGA–ELM (roulette wheel) model.
Table 4.
Evaluation results based on OGA–ELM (K-tournament) model.
Table 5.
Evaluation results based on OGA–ELM (random) model.
Fig 18.
ROC of the NN for the highest result.
Table 6.
Evaluation results based on NN.
Fig 19.
ROC of the ELM for the highest result.
Fig 20.
ROC of the FLN for the highest result.
Table 7.
Evaluation results based on basic ELM.
Table 8.
Evaluation results based on FLN.
Fig 21.
ROC of the SVM for the highest result.
Table 9.
Evaluation results based on SVM.
Fig 22.
ROC of the CNN for the highest result.
Table 10.
The CNN architecture factors.
Table 11.
The trained model parameters used in COVID-19 detection.
Fig 23.
The highest achieved accuracy for all methods.
Table 12.
Evaluation results based on CNN.
Table 13.
Comparison of accuracies between methods.